The paper presents a new approach to the human reindetification problem using covariance features. In many cases, a distance operator between signatures, based on generalized eigenvalues, has to be computed efficiently, especially once the real-time response time is expected from the system. This is a challenging problem as many procedures are in fact computationally intensive tasks and must be repeated constantly. To deal with this problem we have successfully designed and then tested a new video surveillance system. To obtain the required high efficiency we took the advantage of highly parallel computing architectures such as FPGA, GPU and CPU units to perform calculations. However, we had to propose a new GPU-based implementation of the distance operator for querying the example database. Thus, in this paper we present experimental evaluation of the proposed solution in the light of the database response time depending on its size.