To improve Reliability Centered Maintenance (RCM) analysis efficiency, the Artificial Intelligence (AI) technology, such as case-based reasoning (CBR) is successfully introduced into RCM analysis process and an intelligent RCM analysis (IRCMA) was studied, and an intelligent RCM analysis system (IRCMAS) was developed. The idea for IRCMAS is based on the fact that the historical records of RCM analysis on similar items can be referenced and used for the current RCM analysis of a new item. Case retrieval is the key part of the IRCMAS, of which mechanism has an importance effect on reasoning efficiency of system. In this paper, the IRCMAS is introduced, retrieval mechanism and process of cases are presented, and nearest neighbor retrieval method based on analytic hierarchy process (AHP) is in detail discussed by an example. Design of case retrieval mechanism lays steady foundation for development and realization of intelligent RCM analysis system.