Retrieval of 3D shapes, especially non-rigid shapes, is attracting growing interest in the research community. In this paper, a new robust feature points extraction method based on two major approaches is presented. The proposed method is proven to be robust when applied to non-rigid 3D shapes as well as highly replicable in different scales. In addition, since partial features provide more detailed information regarding non-rigid 3D shape retrieval, a representation combining the global partial descriptors for 3D shape retrieval is developed and a new similarity measurement is applied to the corresponding parts of different shapes. Finally, the proposed method is implemented using global and partial descriptors with different weights. The results indicate that the proposed method efficiently performed non-rigid 3D shape retrieval.