Nowadays, fifth-generation (5G) technology is promoted to support massive data transmissions and low-latency communications, which enables diverse vehicular applications. There have been some studies discussing the use of vehicle clustering to save scarce spectrum resources, and prevent network congestions in hybrid cellular/IEEE 802.11p vehicular environments. However, different types of applications could have different levels of quality-of-service (QoS) requirements, and thus this issue should be considered in the clustering of vehicles. We propose a novel vehicle clustering scheme that utilizes the global view and programmable advantage of software defined networking (SDN) technology to conduct an efficient clustering in vehicular environments. The proposed scheme first classifies the existing applications to three different types, the delay-sensitive type, traffic-intensive type, and computation-intensive type, according to the QoS requirements. Then the scheme forms three different clusters based on this classification to satisfy the QoS requirement for each type. We use computer simulations to show the advantage of the proposed scheme over the conventional approach.