Human Body Parts disease is a major health problem and it aspects a large number of people. Human Body Parts disease is the leading cause of death in the modern world. Unless detected Associate in Nursing treated at an early stage it'll cause sickness and causes death. It is also helpful for conducting detailed study and investigations about the nature of the body parts. Content-based image retrieval (CBIR) is a technology that could aid medical diagnosis by retrieving and presenting earlier reported cases that are related to the one being diagnosed. To retrieve relevant cases, CBIR systems depend on super-vise learning to map low-level image contents to high-level diagnostic concepts. A new technique used that automatically learns the similarity between the several exams from textual distances extracted from radiology reports, there by successfully reducing the number of annotations needed. The method used first infers the relation between patients by using information retrieval techniques to determine the textual distances between patient radiology reports. These distances are used by metric learning algorithm that transforms the image space accordingly to textual distances. CBIR systems with different image descriptors and different levels of medical annotations were evaluated, with and without supervision from textual distances, using a database of computer tomography scans of patients with interstitial Human Body Parts diseases. However, the annotation by medical doctors for training and evaluation purposes is a difficult and time-consuming task, which restricts the supervised learning phase to specific CBIR problems of well-defined clinical applications.