In this paper, medical images are used to realize the Computer-Aided Diagnosis (CAD) system, which develops targeted solutions to existing problems. Relying on the MiCOM platform, this system has collected and collated cases of all kinds, based on which a unified data model is constructed according to the gold standard derived by deducting each instance. Afterwards, the object segmentation algorithm is employed to segment the diseased tissues. Edge modification and feature extraction are performed for the tissue block segmented. The features extracted are classified by applying support vector machines or the Naive Bayesian classification algorithm. From the simulation results, the CAD system developed in this paper allows the realization of diagnosis and treatment and sharing of data resources.