Gear mechanisms are widely used in rotating machinery. For this reason, gear health monitoring has been the subject of intensive investigation and research. Among several other methods, vibration measurement and analysis is considered as the most general basis for fault detection. Practical condition monitoring systems need quantities that can be used as features for the diagnostic procedure. In this work energy-based features are proposed. The instantaneous energy density calculated using advanced signal processing techniques, is shown to obtain high values when defected teeth are engaged and consequently can be directly related to damage magnitude.