Microtubules (MT) are filamentous cytoskeletal structures composed of tubulin protein subunits. Through their dynamic behaviors, they participate in many essential cellular functions. MT dynamics are traditionally analyzed from time lapse images by manual techniques that are laborious, approximate and often of limited analytical value. Recently, computational methods have been applied to the problems of detection and tracking of MTs in live cell images. In this paper, we discuss computational methods for extracting dynamics features from live cell MT image sequences. We provide examples of how these features can be used in MT dynamics analysis and improve the manual analytical capabilities.