Banking product extension is a source of widespread information and advertisement, especially fluently supported by Internet media. Case-Based Reasoning (CBR) is an Artificial Intelligence method being used as extension tool, with e-commerce as fast growing application field. Article presents the methodology of applying similarity measures of CBR method to extract bank account products most similar to presented customer preferences. Local similarity measures as well as global similarity measure are described for each account attribute. Computer application based on this method was created within project and applied to search banking products. Real world data of 142 Polish banks’ accounts were used in computations. Examples of search for an account are presented to show searching results and different case adaptation techniques.